Spaces:
Sleeping
Sleeping
File size: 9,055 Bytes
6b67b82 e02dc08 6b67b82 12bc706 6b67b82 fff9411 6b67b82 b8d6301 6b67b82 cdf75a8 6b67b82 cdf75a8 6b67b82 cdf75a8 6b67b82 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 |
from fastapi import FastAPI
# Define the FastAPI app
app = FastAPI(docs_url="/")
@app.get("/search={query}&similarity={similarity}")
def search(query, similarity=False):
import time
import requests
start_time = time.time()
# Set the API endpoint and query parameters
url = "https://www.googleapis.com/books/v1/volumes"
params = {"q": str(query), "printType": "books", "maxResults": 10}
# Send a GET request to the API with the specified parameters
response = requests.get(url, params=params)
# Initialize the lists to store the results
titles = []
authors = []
publishers = []
descriptions = []
images = []
# Parse the response JSON and append the results
data = response.json()
for item in data["items"]:
volume_info = item["volumeInfo"]
try:
titles.append(f"{volume_info['title']}: {volume_info['subtitle']}")
except KeyError:
titles.append(volume_info["title"])
try:
descriptions.append(volume_info["description"])
except KeyError:
descriptions.append("Null")
try:
publishers.append(volume_info["publisher"])
except KeyError:
publishers.append("Null")
try:
authors.append(volume_info["authors"][0])
except KeyError:
authors.append("Null")
try:
images.append(volume_info["imageLinks"]["thumbnail"])
except KeyError:
images.append(
"https://bookstoreromanceday.org/wp-content/uploads/2020/08/book-cover-placeholder.png"
)
### Openalex ###
import pyalex
from pyalex import Works
# Add email to the config
pyalex.config.email = "ber2mir@gmail.com"
# Define a pager object with the same query
pager = Works().search(str(query)).paginate(per_page=10, n_max=10)
# Generate a list of the results
openalex_results = list(pager)
# Get the titles, descriptions, and publishers and append them to the lists
for result in openalex_results[0]:
try:
titles.append(result["title"])
except KeyError:
titles.append("Null")
try:
descriptions.append(result["abstract"])
except KeyError:
descriptions.append("Null")
try:
publishers.append(result["host_venue"]["publisher"])
except KeyError:
publishers.append("Null")
try:
authors.append(result["authorships"][0]["author"]["display_name"])
except KeyError:
authors.append("Null")
images.append(
"https://bookstoreromanceday.org/wp-content/uploads/2020/08/book-cover-placeholder.png"
)
### OpenAI ###
import openai
# Set the OpenAI API key
openai.api_key = "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"
# Create ChatGPT query
chatgpt_response = openai.ChatCompletion.create(
model="gpt-3.5-turbo",
messages=[
{
"role": "system",
"content": "You are a librarian. You are helping a patron find a book.",
},
{
"role": "user",
"content": f"Recommend me 10 books about {query}. Your response should be like: 'title: <title>, author: <author>, publisher: <publisher>, summary: <summary>'",
},
],
)
# Split the response into a list of results
chatgpt_results = chatgpt_response["choices"][0]["message"]["content"].split("\n")[
2::2
]
# Define a function to parse the results
def parse_result(result, ordered_keys=["Title", "Author", "Publisher", "Summary"]):
# Create a dict to store the key-value pairs
parsed_result = {}
for key in ordered_keys:
# Split the result string by the key and append the value to the list
if key != ordered_keys[-1]:
parsed_result[key] = result.split(f"{key}: ")[1].split(",")[0]
else:
parsed_result[key] = result.split(f"{key}: ")[1]
return parsed_result
ordered_keys = ["Title", "Author", "Publisher", "Summary"]
for result in chatgpt_results:
try:
# Parse the result
parsed_result = parse_result(result, ordered_keys=ordered_keys)
# Append the parsed result to the lists
titles.append(parsed_result["Title"])
authors.append(parsed_result["Author"])
publishers.append(parsed_result["Publisher"])
descriptions.append(parsed_result["Summary"])
images.append(
"https://bookstoreromanceday.org/wp-content/uploads/2020/08/book-cover-placeholder.png"
)
# In case the OpenAI API hits the limit
except IndexError:
break
### Prediction ###
from transformers import (
AutoTokenizer,
AutoModelForSeq2SeqLM,
AutoModelForSequenceClassification,
pipeline,
)
from sentence_transformers import SentenceTransformer, CrossEncoder
from sentence_transformers.util import cos_sim, dot_score
# Load the classifiers
# classifier = TextClassifier.load(
# "trainers/deberta-v3-base-tasksource-nli/best-model.pt"
# )
# sentence_transformer = SentenceTransformer("all-MiniLM-L12-v2")
# cross_encoder = CrossEncoder("cross-encoder/stsb-distilroberta-base")
# Combine title, description, and publisher into a single string
combined_data = [
f"{title} {description} {publisher}"
for title, description, publisher in zip(titles, descriptions, publishers)
]
# Prepare the Sentence object
# sentences = [
# Sentence(doc, use_tokenizer=SegtokTokenizer()) for doc in combined_data
# ]
# Classify the sentences
# classifier.predict(sentences)
# Get the predicted labels
# classes = [sentence.labels for sentence in sentences]
# Define the summarizer model and tokenizer
sum_tokenizer = AutoTokenizer.from_pretrained("lidiya/bart-base-samsum")
# sum_model = AutoModelForSeq2SeqLM.from_pretrained("sshleifer/distilbart-xsum-12-6")
sum_model = AutoModelForSeq2SeqLM.from_pretrained("lidiya/bart-base-samsum")
summarizer_pipeline = pipeline(
"summarization",
model=sum_model,
tokenizer=sum_tokenizer,
batch_size=64,
)
# Define the zero-shot classifier
zs_tokenizer = AutoTokenizer.from_pretrained(
"sileod/deberta-v3-base-tasksource-nli"
)
# Quickfix for the tokenizer
# zs_tokenizer.model_input_names = ["input_ids", "attention_mask"]
zs_model = AutoModelForSequenceClassification.from_pretrained(
"sileod/deberta-v3-base-tasksource-nli"
)
zs_classifier = pipeline(
"zero-shot-classification",
model=zs_model,
tokenizer=zs_tokenizer,
batch_size=64,
hypothesis_template="This book is {}.",
multi_label=True,
)
# Summarize the descriptions
summaries = [
summarizer_pipeline(description[0:1024])
if (description != None)
else [{"summary_text": "Null"}]
for description in descriptions
]
# Predict the level of the book
candidate_labels = [
"Introductory",
"Advanced",
"Academic",
"Not Academic",
"Manual",
]
# Get the predicted labels
classes = [zs_classifier(doc, candidate_labels) for doc in combined_data]
# Calculate the elapsed time
end_time = time.time()
runtime = f"{end_time - start_time:.2f} seconds"
# Calculate the similarity between the books
if similarity:
from sentence_transformers import util
sentence_transformer = SentenceTransformer("all-MiniLM-L6-v2")
book_embeddings = sentence_transformer.encode(
combined_data, convert_to_tensor=True
)
similar_books = []
for i in range(len(titles)):
current_embedding = book_embeddings[i]
similarity_sorted = util.semantic_search(
current_embedding, book_embeddings, top_k=20
)
similar_books.append(
{
"sorted_by_similarity": similarity_sorted[0][1:],
}
)
# Create a list of dictionaries to store the results
results = []
for i in range(len(titles)):
results.append(
{
"id": i,
"title": titles[i],
"author": authors[i],
"publisher": publishers[i],
"image_link": images[i],
"labels": classes[i]["labels"][0:2],
"label_confidences": classes[i]["scores"][0:2],
"summary": summaries[i][0]["summary_text"],
"similar_books": similar_books[i]["sorted_by_similarity"],
"runtime": runtime,
}
)
return results
|